© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6848
    Prev
    Next
    INDEX
    Explanations

    code annotations and import statements

    oai_token-act-pair · gemini-2.0-flash

    Java code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.62
     in
    -0.56
     or
    -0.54
     and
    -0.52
    /
    -0.49
    apit
    -0.48
     for
    -0.47
     to
    -0.45
    "
    -0.45
     with
    -0.43
    POSITIVE LOGITS
     itſelf
    0.89
     pleaſure
    0.88
    ſelf
    0.78
    ſelves
    0.77
     myſelf
    0.76
     ་་
    0.75
     ―――――
    0.73
     ſeveral
    0.73
     reaſon
    0.71
     iſt
    0.71
    Activations Density 7.041%

    No Known Activations